Text processing method for a digital camera
View Patent ↗Embodiments disclose a technique to recognize text in a current frame of an image in a view finder of a digital camera. In accordance with the technique, text at a marker (e.g. a cursor or cross hairs) associated with the view finder is recognized and a lookup is performed based on the recognized text. Advantageously, the lookup yields useful information e.g. a translation of a recognized word that is displayed in the viewfinder adjacent to the text. The current frame is not captured by a user. As the user moves the camera to position a new word at the marker, the view finder is updated to provide lookup results associated with the new word. Lookups may be performed of a bilingual dictionary, a monolingual dictionary, a reference book, a travel guide, etc. Embodiments of the invention also cover digital cameras or mobile devices that implement the aforementioned technique.
1. A method for a mobile device equipped with a digital camera, the method comprising:
detecting a plurality of frames by the mobile device;
detecting text in a current frame of the detected plurality of frames for an image associated with a viewfinder of the mobile device;
performing recognition of the detected text which produces a recognized text without freezing the current frame on the viewfinder;
performing a linguistic morphology analysis of the recognized text, wherein the linguistic morphology analysis includes obtaining one or more base dictionary forms for one or more words of the recognized text;
performing a lookup operation based on the one or more base dictionary forms wherein the lookup operation returns a plurality of translations of the base dictionary form wherein the plurality of the translations is limited based upon at least one of the following factors:
frequency of the translations of the base dictionary form used, and additional context information associated with one or more of the base dictionary forms; and
displaying a translation result of the lookup operation in the viewfinder.
2. The method of claim 1 , wherein said detecting the plurality of frames by the mobile device is performed without capturing the current frame for the image associated with the viewfinder.
3. The method of claim 1 , wherein detecting the text includes analyzing a rectangular area of the current frame centered on a marker associated with the viewfinder.
4. The method of claim 3 , wherein displaying the result includes displaying the result of the lookup operation without interrupting displaying of the current frame in the viewfinder.
5. The method of claim 3 , wherein the result is displayed in the viewfinder in proximity to the detected text.
6. The method of claim 1 , wherein the lookup operation includes translating the one or more base dictionary forms into a target language.
7. The method of claim 6 , further comprising allowing a user to specify the target language.
8. The method of claim 1 , wherein the lookup operation includes a lookup of at least one of a bilingual dictionary, a monolingual dictionary, a reference book, and a travel guide.
9. The method of claim 1 , further comprising providing recorded audio associated with the result of the lookup operation.
10. The method of claim 9 , wherein the recording audio includes an audio pronunciation of the recognized text.
11. The method of claim 1 , wherein the lookup operation includes accessing a remote server over a wireless data path.
12. The method of claim 3 , further comprising selectively updating the recognized text based on a detected camera movement.
13. The method of claim 12 , wherein selectively updating the recognized text includes performing recognition of detected text of a later-in-time frame when the marker is outside the rectangular area in the later-in-time frame.
14. A mobile device comprising
a processor;
a digital camera capable of detecting a plurality of frames; and
a memory storing instructions which, when executed by the processor, cause the processor to:
(a) detect text in a current frame of the detected plurality of frames for an image associated with a viewfinder of the mobile device;
(b) perform recognition of the detected text which produces a recognized text without freezing the current frame on the viewfinder;
(c) perform a linguistic morphology analysis on the recognized text, wherein the linguistic morphology analysis includes obtaining one or more base dictionary forms for one or more words of the recognized text;
(d) perform a lookup operation based on the one or more base dictionary forms dictionary form wherein the plurality of the translations is limited based upon at least one of the following factors:
frequency of the translations of the base dictionary form used, additional context information associated with one or more of the base dictionary forms; and
(e) display a translation result of the lookup operation in the viewfinder.
15. The mobile device of claim 14 , wherein the steps (a) to (e) are performed without capturing the current frame for the image in the viewfinder.
16. The mobile device of claim 14 , wherein detecting the text includes analyzing a rectangular area of the current frame centered on a marker associated with the viewfinder.
17. The mobile device of claim 16 , wherein displaying the result comprises displaying the result without interrupting displaying of the current frame in the viewfinder.
18. The mobile device of claim 16 , wherein the result is displayed in the viewfinder in proximity to the detected text.
19. The mobile device of claim 14 , wherein the lookup operation includes translating the one or more base dictionary forms into a target language.
20. The mobile device of claim 19 , further comprising allowing a user to specify the target language.
21. The mobile device of claim 14 , wherein the lookup operation includes a lookup of at least one of a bilingual dictionary, a monolingual dictionary, a reference book, and a travel guide.
22. The mobile device of claim 14 , further comprising providing recorded audio associated with the result of the lookup operation.
23. The mobile device of claim 22 , wherein the recording audio comprises an audio pronunciation of the recognized text.
24. The mobile device of claim 14 , wherein the lookup operation includes accessing a remote server over a wireless data path.
25. The mobile device of claim 16 , further comprising selectively updating the recognized text based on a detected camera movement.
26. The mobile device of claim 25 , wherein selectively updating the recognized text includes performing recognition of detected text of a late-in-time frame when the marker is outside the rectangular area in the later- in-time frame.